Real-time personalization product tracking B2B/B2C

1. A method for scheduling and mapping functionality in a computer application implemented by one or more processors operatively coupled to a non-transitory computer readable storage device, on which are stored modules of instruction code that when executed cause the one or more processors to perform the following steps: determining user behavior based on detected input and different types of feature usage based on analyzing communication requests and responses between a client device and application services, without requiring prior knowledge of coding of the application to track feature usage; wherein user behavior is determined based on learning through a training phase for the application associating detected different types of features with an identified unique identifier and analyzed event flows, clicks, and text elements, whereby no prior knowledge of coding is required; creating a product adoption learning model based on learned user behavior and profile by applying a training algorithm of exposure feature usage pattern in relation to user behavior action following the feature usage of the user throughout a product lifecycle; determining in real time a feature adoption schedule and time window based on user real-time current behavior during a time period while the feature adoption schedule is being determined, user profile and feature usage, by applying the adoption learning model.

2. The method of claim 1 wherein creating the adoption learning model further includes analyzing a user behavior action, after feature usage by identifying engagement or adoption actions indicating a successful usage of the application, feature or module.

3. The method of claim 1 wherein the creating the adoption learning model further includes identifying high value features which lead to successful and shorter time of feature adoption.

4. The method of claim 1 wherein the creation of the adoption learning model further comprises detecting an effective time window of feature adoption, by statistically analyzing a number of users adopting the feature within each time period.

5. The method of claim 1 wherein the user behavior learning further comprises analyzing a sequence of document object model (DOM) elements for identifying user actions and usage of features of the application, features or modules.

6. The method of claim 1 further comprising the step of detecting application features using a learning algorithm based on analyzing communication requests and responses between the client device and a personalization system.

7. The method of claim 1 further comprising the step of determining a next best action by applying the adoption learning model based on user current behavior, user profile and feature usage.

8. The method of claim 1 further comprising, on each product release, auto-detecting unique identifiers within a DOM page which are associated with the product release features or actions and automatically recomputing the identifiers in case of a change.

9. The method of claim 8 further comprising the step of detecting features/actions applied by analyzing sequences of detected unique identifiers.

10. The method of claim 1 wherein the user behavior learning comprises using cascading style sheets (CSS) selectors for identifying unique identifiers within a DOM page based on Xpath navigation through an HTML/XML document, CSS class, HTML ID or relative path anchor elements, whereby prior knowledge of the features or coding of the application is not required.

11. The method of claim 1 further comprising the step of creating a product tree, wherein the tree has a multiple level hierarchy containing sub modules and features visualizing feature usage patterns, wherein each feature is represented by a set of elements and rules that are used by a tracking system to associate user action/clicks with the features in each level.

12. A system for scheduling and mapping functionality in a computer application, said system comprising a non-transitory storage device and one or more processing devices operatively coupled to the storage device on which are stored modules of instruction code executable by the one or more processors, the system comprising: a learning module for determining user behavior based on detected input and different types of feature usage based on analyzing communication requests and responses between a client device and application services, without requiring prior knowledge of coding of the application to track feature usage; wherein user behavior is determined based on learning through a training phase for the application associating detected different types of features with an identified unique identifier and analyzed event flows, clicks, and text elements, whereby no prior knowledge of coding is required; a feature adoption analysis module creating a product adoption learning model based on user behavior and profile by applying a training algorithm of feature usage in relation to user behavior action and following the feature usage of the user throughout a product lifecycle; a feature recommendation module for determining in real time a feature adoption schedule and time window based on user real-time current behavior during a time period while the feature adoption schedule is being determined, user profile and feature usage, by applying the adoption learning model.

13. The system of claim 12 wherein the adoption learning model analyzes user behavior action, after feature usage by identifying engagement or adoption actions indicating a successful usage of the application, feature or module.

14. The system of claim 12 wherein the adoption learning model identifies high value features which lead to successful and shorter time of feature adoption.

15. The system of claim 12 wherein the adoption learning model detects an effective time window of feature adoption, by statistically analyzing a number of users adopting the feature within each time period.

16. The system of claim 12 wherein the user behavior learning comprises analyzing a sequence of DOM elements for identifying user actions and usage of features of the application, features or modules.

17. The system of claim 12 wherein the learning module further comprising the step of detecting application features using a learning algorithm based on analyzing communication requests and responses between the client device and a personalization system.

18. The system of claim 12 wherein the feature adoption analysis module personalizes content and determines a next best action by applying the adoption learning model based on user current behavior, user profile and feature usage.

19. The system of claim 12 wherein on each product release unique identifiers are auto-detected and the identifiers are automatically recomputed in case of a change.

20. A method for mapping functionality in a computer application implemented by one or more processors operatively coupled to a non-transitory computer readable storage device, on which are stored modules of instruction code that when executed cause the one or more processors to perform the following steps: determining user behavior based on detected input and different types of feature usage based on analyzing communication requests and responses between a client device and application services, without requiring prior knowledge of coding of the application to track feature usage; wherein user behavior is determined based on learning through a training phase for the application associating detected different types of features with an identified unique identifier and analyzed event flows, clicks, and text elements, whereby no prior knowledge of coding is required; applying a training algorithm of exposure feature usage pattern in relation to user behavior action following a sequence of feature usage of the user for identifying action flow patterns of different types of feature usage; creating a product tree and usage flow using the identified action sequences/learnt patterns of different types of feature usage, based on learning algorithm products, wherein the tree has a multiple level hierarchy containing sub modules and features visualizing feature usage patterns, wherein each feature is represented by a set of elements and rules that are used by a tracking system to associate user action/clicks with the features in each level; and based on an adoption learning module automatically recommending a next best action and tune in-application engagements, determining an action flow sequence based on views or clicks and user intent, by learning which engagements, guides, or special offers have higher chances of being clicked by users based on an identified product feature mapper.